Urine surface-enhanced Raman spectroscopy combined with SVM algorithm for rapid diagnosis of liver cirrhosis and hepatocellular carcinoma

Photodiagnosis Photodyn Ther. 2022 Jun:38:102811. doi: 10.1016/j.pdpdt.2022.102811. Epub 2022 Mar 15.

Abstract

In this paper, we investigated the feasibility of using urine for surface-enhanced Raman spectroscopy (SERS) for the rapid screening of patients with liver cirrhosis and hepatocellular carcinoma (HCC). The SERS spectra were recorded from the urine of 49 liver cirrhosis, 55 HCC, and 50 healthy volunteers using a Raman spectrometer. The normalized mean Raman spectra showed the difference of specific biomolecules associated with the illnesses, and the metabolism of specific nucleic acids and amino acids is abnormal in patients with liver cirrhosis and HCC. Based on the SVM algorithm, the urine SERS method could identify liver cirrhosis (sensitivity 88.9%, specificity 83.3%, and accuracy 85.9%) and HCC (sensitivity 85.5%, specificity 84.0%, and accuracy 84.8%). It has a higher diagnostic sensitivity for HCC than serum Alpha fetoprotein (AFP). This exploratory study showed that the urine SERS spectra combined with the SVM algorithm has indicated great potential in the noninvasive identification of liver cirrhosis and HCC.

Keywords: Alpha fetoprotein (AFP); Diagnosis; Hepatocellular carcinoma (HCC); Liver cirrhosis; Support vector machine (SVM); Surface-enhanced Raman spectroscopy (SERS); Urine.

MeSH terms

  • Algorithms
  • Biomarkers, Tumor
  • Carcinoma, Hepatocellular* / diagnosis
  • Humans
  • Liver Cirrhosis / diagnosis
  • Liver Neoplasms* / diagnosis
  • Photochemotherapy* / methods
  • Sensitivity and Specificity
  • Spectrum Analysis, Raman / methods
  • Support Vector Machine

Substances

  • Biomarkers, Tumor